Artificial Neural Network, Quantile and Semi-Log Regression Modelling of Mass Appraisal in Housing

We used a large sample of 188,652 properties, which represented 4.88% the total housing stock in Catalonia from 1994 to 2013, make comparison between different real estate valuation methods based on artificial neural networks (ANNs), quantile regressions (QRs) and semi-log (SLRs). A literature gap regard ANN QR modelling hedonic prices was identified, with this article being first paper include comparison. Therefore, study aimed answer (1) whether market is an alternative ANNs, (2) it confirmed that ANNs produce better results than SLRs when assessing Catalonia, (3) three mass appraisal models should be by Spanish banks assess estate. The suggested obtained similar performances QRs performed datasets were smaller. not found could properties whereas small medium use SLRs, either or appraisal.